config.n_cells = config.n_layers
# double the number of cells for bidirectional networks
if config.birnn:
config.n_cells *= 2
if args.resume_snapshot:
model = torch.load(args.resume_snapshot, map_location=device)
else:
model = SNLIClassifier(config)
if args.word_vectors:
model.embed.weight.data.copy_(inputs.vocab.vectors)
model.to(device)
criterion = nn.CrossEntropyLoss()
opt = O.Adam(model.parameters(), lr=args.lr)
iterations = 0
start = time.time()
best_dev_acc = -1
train_iter.repeat = False
header = ' Time Epoch Iteration Progress (%Epoch) Loss Dev/Loss Accuracy Dev/Accuracy'
dev_log_template = ' '.join(
'{:>6.0f},{:>5.0f},{:>9.0f},{:>5.0f}/{:<5.0f} {:>7.0f}%,{:>8.6f},{:8.6f},{:12.4f},{:12.4f}'
.split(','))
log_template = ' '.join(
'{:>6.0f},{:>5.0f},{:>9.0f},{:>5.0f}/{:<5.0f} {:>7.0f}%,{:>8.6f},{},{:12.4f},{}'
.split(','))
makedirs(args.save_path)
print(header)
config.n_embed = len(inputs.vocab)
config.d_out = len(answers.vocab)
config.n_cells = config.n_layers
if config.birnn:
config.n_cells *= 2
if args.resume_snapshot:
model = torch.load(args.resume_snapshot, map_location=lambda storage, locatoin: storage.cuda(args.gpu))
else:
model = SNLIClassifier(config)
if args.word_vectors:
model.embed.weight.data = inputs.vocab.vectors
model.cuda()
criterion = nn.CrossEntropyLoss()
opt = O.Adam(model.parameters(), lr=args.lr)
iterations = 0
start = time.time()
best_dev_acc = -1
train_iter.repeat = False
header = ' Time Epoch Iteration Progress (%Epoch) Loss Dev/Loss Accuracy Dev/Accuracy'
dev_log_template = ' '.join('{:>6.0f},{:>5.0f},{:>9.0f},{:>5.0f}/{:<5.0f} {:>7.0f}%,{:>8.6f},{:8.6f},{:12.4f},{:12.4f}'.split(','))
log_template = ' '.join('{:>6.0f},{:>5.0f},{:>9.0f},{:>5.0f}/{:<5.0f} {:>7.0f}%,{:>8.6f},{},{:12.4f},{}'.split(','))
os.makedirs(args.save_path, exist_ok=True)
print(header)
for epoch in range(args.epochs):
train_iter.init_epoch()
n_correct, n_total = 0, 0
for batch_idx, batch in enumerate(train_iter):
else:
config.regularization = 0
model = SNLIClassifier(config)
if config.spinn:
model.out[len(model.out._modules) - 1].weight.data.uniform_(-0.005, 0.005)
if args.word_vectors:
model.embed.weight.data = inputs.vocab.vectors
if args.gpu != -1:
model.cuda()
if args.resume_snapshot:
model.load_state_dict(torch.load(args.resume_snapshot))
criterion = nn.CrossEntropyLoss()
#opt = optim.Adam(model.parameters(), lr=args.lr)
opt = optim.RMSprop(model.parameters(),
lr=config.lr,
alpha=0.9,
eps=1e-6,
weight_decay=config.regularization)
iterations = 0
start = time.time()
best_dev_acc = -1
train_iter.repeat = False
header = ' Time Epoch Iteration Progress (%Epoch) Loss Dev/Loss Accuracy Dev/Accuracy'
dev_log_template = ' '.join(
'{:>6.0f},{:>5.0f},{:>9.0f},{:>5.0f}/{:<5.0f} {:>7.0f}%,{:>8.6f},{:8.6f},{:12.4f},{:12.4f}'
.split(','))
log_template = ' '.join(
'{:>6.0f},{:>5.0f},{:>9.0f},{:>5.0f}/{:<5.0f} {:>7.0f}%,{:>8.6f},{},{:12.4f},{}'
config.d_mlp = 1024
config.d_hidden = 300
config.d_embed = 300
config.d_proj = 600
torch.backends.cudnn.enabled = False
else:
config.regularization = 0
model = SNLIClassifier(config)
if config.spinn:
model.out[len(model.out._modules) - 1].weight.data.uniform_(-0.005, 0.005)
if args.word_vectors:
model.embed.weight.data = inputs.vocab.vectors
if args.gpu != -1:
model.cuda()
print(next(model.parameters()).is_cuda)
if args.resume_snapshot:
model.load_state_dict(torch.load(args.resume_snapshot))
criterion = nn.CrossEntropyLoss()
#opt = optim.Adam(model.parameters(), lr=args.lr)
opt = optim.RMSprop(model.parameters(),
lr=config.lr,
alpha=0.9,
eps=1e-6,
weight_decay=config.regularization)
iterations = 0
start = time.time()
best_dev_acc = -1
train_iter.repeat = False
config.mlp_dropout = dropout
config.embed_dropout = dropout
config.d_tracker = tracker_dim
config.birnn = birnn
config.d_mlp = mlp_dimension
config.predict = predict_transitions
config.n_mlp_layers = n_mlp_layers
if birnn:
config.n_cells *= 2
model = SNLIClassifier(config)
model.embed.weight.data = inputs.vocab.vectors
model.to(device)
criterion = nn.CrossEntropyLoss()
opt = optim.Adam(model.parameters(), lr=lr)
iterations = 0
start = time.time()
best_dev_acc = -1
train_iter.repeat = False
header = ' Time Epoch Iteration Progress (%Epoch) Loss Dev/Loss Accuracy Dev/Accuracy'
dev_log_template = ' '.join(
'{:>6.0f},{:>5.0f},{:>9.0f},{:>5.0f}/{:<5.0f} {:>7.0f}%,{:>8.6f},{:8.6f},{:12.4f},{:12.4f}'
.split(','))
log_template = ' '.join(
'{:>6.0f},{:>5.0f},{:>9.0f},{:>5.0f}/{:<5.0f} {:>7.0f}%,{:>8.6f},{},{:12.4f},{}'
.split(','))
print(header)
